import pandas as pd
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
import joblib

# Load the data CSV
data = pd.read_csv("creditcard.csv")

# Features and target
X = data.drop(columns=["Class"])
y = data["Class"]

# Split into train and test sets (optional, good practice)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Train model
model = RandomForestClassifier(n_estimators=100, random_state=42)
model.fit(X_train, y_train)

# Save the model to a file
joblib.dump(model, "fraud_detector.pkl")
print("Model training complete and saved as fraud_detector.pkl")